feat: an album holding a song twice beside its single keeps one copy (#5401)

A cross-release group was only ever linked, never merged, so an album that held the song twice among the releases kept both: Humanz has Saturnz Barz, Andromeda, We Got the Power and Garage Palace as its FLAC and a YouTube mp3, each beside the single. The resolver now merges an album's extra copies into its best (the one that is not a video rip, else ProposeSurvivor: lossless first) with ReplaceTrack, history and all, then links what is left as one song. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-20 11:55:23 -04:00
parent 80ecc2f7e7
commit 09e74a57a2
2 changed files with 192 additions and 1 deletions
@@ -27,7 +27,10 @@ import (
 //   - On one album, a song is held once: the extra copies are merged into the
 //     best by ProposeSurvivor.
 //   - Across releases, each copy belongs to its own release (a single and its
-//     album): nothing is removed, and the copies are linked as one song.
+//     album): nothing is removed, and the copies are linked as one song. An
+//     album holding the song twice among them still holds it once: its extra
+//     copies are merged into its best (Humanz held Saturnz Barz twice beside
+//     the single, #5401).
 //   - Except that a video rip is no release's copy. When every copy but one is
 //     a rip, across releases or under another title, the rips are merged into
 //     the one that is not.
@@ -215,6 +218,10 @@ func ResolveDuplicatesWith(
 		}
 	}

+	folded, foldedNames := foldAlbumCopies(ctx, pool, logger, dataDir, groups, merged, resolveMergeCap-res.Merged)
+	res.Merged += folded
+	mergedNames = append(mergedNames, foldedNames...)
+
 	res.Dismissed = dismissDistinct(ctx, pool, logger, groups, merged)
 	wrong, names := settleWrongSlots(ctx, pool, logger, groups, merged, src)
 	res.WrongFiles = wrong
@@ -235,6 +242,123 @@ func ResolveDuplicatesWith(
 	return res, nil
 }

+// foldAlbumCopies merges, in each cross-release group, the extra copies one
+// album holds of the song into the best of that album's copies: the one that
+// is not a video rip when only one is not, else ProposeSurvivor's choice. The
+// copies on other releases stay and are linked as one song. At most budget
+// copies go. It returns how many went and the songs they were, and drops them
+// from their groups.
+func foldAlbumCopies(
+	ctx context.Context, pool *pgxpool.Pool, logger *slog.Logger, dataDir string,
+	groups []*resolveGroup, merged map[pgtype.UUID]bool, budget int,
+) (int, []string) {
+	n := 0
+	var names []string
+	for _, g := range groups {
+		if g.class != ClassCrossRelease || merged[g.id] || ctx.Err() != nil || n >= budget {
+			continue
+		}
+		onAlbum := map[string][]int{}
+		for i, m := range g.members {
+			k := syncpkg.FormatUUID(m.AlbumID) + "\x00" + MatchTitleKey(m.Title, m.ArtistName)
+			onAlbum[k] = append(onAlbum[k], i)
+		}
+		gone := map[int]bool{}
+		for _, copies := range onAlbum {
+			if len(copies) < 2 {
+				continue
+			}
+			keep, reason := albumCopySurvivor(g, copies)
+			for _, i := range copies {
+				if i == keep || n >= budget {
+					continue
+				}
+				if err := foldAlbumCopy(ctx, pool, logger, dataDir, g, i, keep, reason); err != nil {
+					logger.Warn("duplicate resolve: merging an album's extra copy failed",
+						"group_id", syncpkg.FormatUUID(g.id), "path", g.members[i].FilePath, "err", err)
+					continue
+				}
+				gone[i] = true
+				n++
+				if len(names) < notifyItems {
+					names = append(names, TrackLabel(g.members[i].ArtistName, g.members[i].Title))
+				}
+			}
+		}
+		if len(gone) > 0 {
+			kept := g.members[:0:0]
+			for i, m := range g.members {
+				if !gone[i] {
+					kept = append(kept, m)
+				}
+			}
+			g.members = kept
+		}
+	}
+	return n, names
+}
+
+// albumCopySurvivor picks which of one album's copies (indexes into the
+// group's members) to keep, and why.
+func albumCopySurvivor(g *resolveGroup, copies []int) (int, string) {
+	notRip := -1
+	for _, i := range copies {
+		if isRip(g.members[i]) {
+			continue
+		}
+		if notRip >= 0 {
+			notRip = -1
+			break
+		}
+		notRip = i
+	}
+	if notRip >= 0 {
+		return notRip, "the copy that is not a video rip"
+	}
+	all := survivorCandidates(g)
+	cands := make([]SurvivorCandidate, len(copies))
+	for j, i := range copies {
+		cands[j] = all[i]
+	}
+	id, reason := ProposeSurvivor(cands)
+	for _, i := range copies {
+		if all[i].TrackID == id {
+			return i, reason
+		}
+	}
+	return copies[0], reason
+}
+
+// foldAlbumCopy replaces one of an album's copies with the copy kept, history
+// and all, and records it as the resolver's merge.
+func foldAlbumCopy(
+	ctx context.Context, pool *pgxpool.Pool, logger *slog.Logger, dataDir string,
+	g *resolveGroup, gone, keep int, reason string,
+) error {
+	from, into := g.members[gone], g.members[keep]
+	moved, err := ReplaceTrack(ctx, pool, logger, dataDir, from.TrackID, into.TrackID)
+	if err != nil {
+		return err
+	}
+	audit.WriteOrLog(ctx, pool, logger, pgtype.UUID{}, pgtype.UUID{}, audit.ActionDuplicateMerge, map[string]any{
+		"automatic":         true,
+		"group_id":          syncpkg.FormatUUID(g.id),
+		"tier":              g.tier,
+		"class":             string(g.class),
+		"survivor_track_id": syncpkg.FormatUUID(into.TrackID),
+		"survivor_path":     into.FilePath,
+		"survivor_reason":   reason + "; the album held the song twice",
+		"removed": []map[string]string{
+			{"track_id": syncpkg.FormatUUID(from.TrackID), "file_path": from.FilePath},
+		},
+		"moved": map[string]any{
+			"play_events": moved.PlayEvents, "skip_events": moved.SkipEvents,
+			"likes": moved.Likes, "playlist_entries": moved.PlaylistEntries,
+		},
+	})
+	return nil
+}
+
 // linkCrossRelease links each cross-release group's copies as one song
 // (#5438): a like on one is a like on all, and the Liked list, shuffle and the
 // mixes count the song once. A group the pass merged has nothing left to link. Linking an already-linked group changes nothing,
@@ -2,6 +2,8 @@ package library

 import (
 	"context"
+	"os"
+	"path/filepath"
 	"testing"

 	"github.com/jackc/pgx/v5/pgtype"
@@ -218,3 +220,68 @@ func songKeys(t *testing.T, q *dbq.Queries, ids ...pgtype.UUID) []pgtype.UUID {
 	}
 	return out
 }
+
+// A cross-release group whose album holds the song twice (Humanz: Saturnz
+// Barz as a FLAC and a YouTube mp3, beside the single, #5401): the album's
+// extra copy is merged into its FLAC, the single stays, and the two copies
+// left are linked as one song.
+func TestResolveDuplicates_FoldsAnAlbumsExtraCopyInACrossReleaseGroup_Integration(t *testing.T) {
+	pool := newPool(t)
+	ctx := context.Background()
+	q := dbq.New(pool)
+	dir := t.TempDir()
+	artist, err := q.UpsertArtist(ctx, dbq.UpsertArtistParams{Name: "Gorillaz", SortName: "Gorillaz"})
+	if err != nil {
+		t.Fatal(err)
+	}
+	track := func(album, name, format string) dbq.Track {
+		t.Helper()
+		a, err := q.UpsertAlbum(ctx, dbq.UpsertAlbumParams{Title: album, SortTitle: album, ArtistID: artist.ID})
+		if err != nil {
+			t.Fatal(err)
+		}
+		path := filepath.Join(dir, album, name)
+		if err := os.MkdirAll(filepath.Dir(path), 0o755); err != nil {
+			t.Fatal(err)
+		}
+		if err := os.WriteFile(path, []byte("audio"), 0o644); err != nil {
+			t.Fatal(err)
+		}
+		tr, err := q.UpsertTrack(ctx, dbq.UpsertTrackParams{
+			Title: "Saturnz Barz", AlbumID: a.ID, ArtistID: artist.ID,
+			DurationMs: 181000, FilePath: path, FileSize: 100, FileFormat: format,
+		})
+		if err != nil {
+			t.Fatal(err)
+		}
+		return tr
+	}
+	flac := track("Humanz", "04 Saturnz Barz.flac", "flac")
+	mp3 := track("Humanz", "06 Saturnz Barz (feat. Popcaan).mp3", "mp3")
+	single := track("Saturnz Barz", "01 Saturnz Barz.mp3", "mp3")
+	var groupID pgtype.UUID
+	if err := pool.QueryRow(ctx,
+		`INSERT INTO duplicate_groups (member_key, tier) VALUES ('humanz-saturnz', 'exact') RETURNING id`,
+	).Scan(&groupID); err != nil {
+		t.Fatal(err)
+	}
+	if _, err := pool.Exec(ctx, `INSERT INTO duplicate_group_members (group_id, track_id) VALUES ($1, $2), ($1, $3), ($1, $4)`,
+		groupID, flac.ID, mp3.ID, single.ID); err != nil {
+		t.Fatal(err)
+	}
+
+	res, err := ResolveDuplicates(ctx, pool, nil, "", true)
+	if err != nil {
+		t.Fatal(err)
+	}
+	if res.Merged != 1 || exists(mp3.FilePath) || !exists(flac.FilePath) || !exists(single.FilePath) {
+		t.Fatalf("result %+v, mp3 %v flac %v single %v; want only the album's mp3 merged away",
+			res, exists(mp3.FilePath), exists(flac.FilePath), exists(single.FilePath))
+	}
+	if _, err := q.GetTrackByID(ctx, mp3.ID); err == nil {
+		t.Error("the album's extra copy is still a track")
+	}
+	if res.SongsLinked != 1 {
+		t.Errorf("songs linked = %d, want the FLAC and the single linked as one song", res.SongsLinked)
+	}
+}